For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed. Within A2J, anchor points able to capture global-local spatial context information are densely set on depth image as local regressors for the joints. They contribute to predict the positions of the joints in ensemble way to enhance generalization ability. The proposed 3D articulated pose estimation paradigm is different from the state-of-the-art encoder-decoder based FCN, 3D CNN and point-set based manners. To discover informative anchor points towards certain joint, anchor proposal procedure is also proposed for A2J. Meanwhile 2D CNN (i.e., ResNet-50) is used as backbone network to drive A2J, without using time-consuming 3D convolutional or deconvolutional layers. The experiments on 3 hand datasets and 2 body datasets verify A2J's superiority. Meanwhile, A2J is of high running speed around 100 FPS on single NVIDIA 1080Ti GPU.

SIL040, an introgression line (IL) developed by introgressing chromosomal segments from an accession of Oryza rufipogon into an indica cultivar Guichao 2, showed significantly less grains per panicle than the recurrent parent Guichao 2. Quantitative trait locus (QTL) analysis in F2 and F3 generations derived from the cross between SIL040 and Guichao 2 revealed that gpa7, a QTL located on the short arm of chromosome 7, was responsible of this variation. Alleles from O. rufipogon decreased grains per panicle. To fine mapping of gpa7, a high-resolution map with 1,966 F2 plants derived from the cross between SIL040 and Guichao 2 using markers flanking gpa7 was constructed, and detailed quantitative evaluation of the structure of main panicle of each of F3 families derived from recombinants screened was performed. By two-step substitution mapping, gpa7 was finally narrowed down to a 35-kb region that contains five predicted genes in cultivated rice. The fact that QTLs for five panicle traits (length of panicle, primary branches per panicle, secondary branches per panicle, grains on primary branches and grains on secondary branches) were all mapped in the same interval as that for gpa7 suggested that this locus was associated with panicle structure, showing pleiotropic effects. The characterizing of panicle structure of IL SIL040 further revealed that, during the domestication from common wild allele to cultivated rice one at gpa7, not only the number of branches and grains per panicle increased significantly, more importantly, but also the ratio of secondary branches per panicle to total branches per panicle and the ratio of grains on secondary branches per panicle to total grains per panicle increased significantly. All these results reinforced the idea that gpa7 might play an important role in the regulation of grain number per panicle and the ratio of secondary branches per panicle during the domestication of rice panicle.

We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and handobject interaction. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set. Unfortunately, since the space of hand poses is highly dimensional, it is inherently not feasible to cover the whole space densely, despite recent efforts in collecting large-scale training datasets. This sampling problem is even more severe when hands are interacting with objects and/or inputs are RGB rather than depth images, as RGB images also vary with lighting conditions and colors. To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. More exactly, HANDS'19 is designed (a) to evaluate the influence of both depth and color modalities on 3D hand pose estimation, under the presence or absence of objects; (b) to assess the generalisation abilities w.r.t. four main axes: shapes, articulations, viewpoints, and objects; (c) to explore the use of a synthetic hand models to fill the gaps of current datasets. Through the challenge, the overall accuracy has dramatically improved over the baseline, especially on extrapolation tasks, from 27mm to 13mm mean joint error. Our analyses highlight the impacts of: Data pre-processing, ensemble approaches, the use of a parametric 3D hand model (MANO), and different HPE methods/backbones.

No abstract

No abstract

Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image. Existing methods perform the same harmonization process for the whole foreground. However, the implanted foreground always contains different appearance patterns. All the existing solutions ignore the difference of each color block and losing some specific details. Therefore, we propose a novel global-local two stages framework for Fine-grained Region-aware Image Harmonization (FRIH), which is trained end-to-end. In the first stage, the whole input foreground mask is used to make a global coarse-grained harmonization. In the second stage, we adaptively cluster the input foreground mask into several submasks by the corresponding pixel RGB values in the composite image. Each submask and the coarsely adjusted image are concatenated respectively and fed into a lightweight cascaded module, adjusting the global harmonization performance according to the region-aware local feature. Moreover, we further designed a fusion prediction module by fusing features from all the cascaded decoder layers together to generate the final result, which could utilize the different degrees of harmonization results comprehensively. Without bells and whistles, our FRIH algorithm achieves the best performance on iHarmony4 dataset (PSNR is 38.19 dB) with a lightweight model. The parameters for our model are only 11.98 M, far below the existing methods.

In this paper, we place the atomic action detection problem into a Long-Short Term Context (LSTC) to analyze how the temporal reliance among video signals affect the action detection results. To do this, we decompose the action recognition pipeline into shortterm and long-term reliance, in terms of the hypothesis that the two kinds of context are conditionally independent given the objective action instance. Within our design, a local aggregation branch is utilized to gather dense and informative short-term cues, while a high order long-term inference branch is designed to reason the objective action class from high-order interaction between actor and other person or person pairs. Both branches independently predict the context-specific actions and the results are merged in the end. We demonstrate that both temporal grains are beneficial to atomic action recognition. On the mainstream benchmarks of atomic action detection, our design can bring significant performance gain from the existing state-of-the-art pipeline. CCS CONCEPTS• Computing methodologies → Activity recognition and understanding.

No abstract